INDEX

Explanations

phrases discussing actions or statements made by individuals

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abil

-0.68

ander

-0.64

WIN

-0.64

houses

-0.64

halla

-0.63

 nurture

-0.63

hips

-0.62

natureconservancy

-0.62

 presided

-0.61

-0.60

POSITIVE LOGITS

 sure

1.04

 noises

0.96

 clear

0.92

 headlines

0.90

 assertions

0.88

 mention

0.83

 dispar

0.83

 insin

0.82

 explicit

0.80

 landfall

0.80

Activations Density 0.122%

phrases discussing actions or statements made by individuals

No Comments

No Known Activations